Search Results for author:
Found 53 papers, 25 papers with code
Local Self-Attention over Long Text for Efficient Document Retrieval
In this work, we propose a local self-attention which considers a moving window over the document terms and for each term attends only to other terms in the same window.
Macaw: An Extensible Conversational Information Seeking Platform
Such research will require data and tools, to allow the implementation and study of conversational systems.
LaMP: When Large Language Models Meet Personalization
This paper highlights the importance of personalization in large language models and introduces the LaMP benchmark -- a novel benchmark for training and evaluating language models for producing personalized outputs.
Optimization Methods for Personalizing Large Language Models through Retrieval Augmentation
This paper studies retrieval-augmented approaches for personalizing large language models (LLMs), which potentially have a substantial impact on various applications and domains.
From Neural Re-Ranking to Neural Ranking: Learning a Sparse Representation for Inverted Indexing
In this work, we propose a standalone neural ranking model (SNRM) by introducing a sparsity property to learn a latent sparse representation for each query and document.
Ranked #12 on
Ad-Hoc Information Retrieval
on TREC Robust04
MIMICS: A Large-Scale Data Collection for Search Clarification
In this paper, we introduce MIMICS, a collection of search clarification datasets for real web search queries sampled from the Bing query logs.
Asking Clarifying Questions in Open-Domain Information-Seeking Conversations
In this paper, we formulate the task of asking clarifying questions in open-domain information-seeking conversational systems.
Scalable and Effective Generative Information Retrieval
This paper represents an important milestone in generative retrieval research by showing, for the first time, that generative retrieval models can be trained to perform effectively on large-scale standard retrieval benchmarks.
Conformer-Kernel with Query Term Independence for Document Retrieval
In this work, we extend the TK architecture to the full retrieval setting by incorporating the query term independence assumption.
Curriculum Learning for Dense Retrieval Distillation
Recent work has shown that more effective dense retrieval models can be obtained by distilling ranking knowledge from an existing base re-ranking model.
CSFCube -- A Test Collection of Computer Science Research Articles for Faceted Query by Example
Query by Example is a well-known information retrieval task in which a document is chosen by the user as the search query and the goal is to retrieve relevant documents from a large collection.
Intra-Document Cascading: Learning to Select Passages for Neural Document Ranking
An emerging recipe for achieving state-of-the-art effectiveness in neural document re-ranking involves utilizing large pre-trained language models - e. g., BERT - to evaluate all individual passages in the document and then aggregating the outputs by pooling or additional Transformer layers.
Context-Aware Target Apps Selection and Recommendation for Enhancing Personal Mobile Assistants
Here we focus on context-aware models to leverage the rich contextual information available to mobile devices.
Passage Retrieval for Outside-Knowledge Visual Question Answering
We first conduct sparse retrieval with BM25 and study expanding the question with object names and image captions.
A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question Answering
Utilizing the passages retrieved by DEDR, we further introduce MM-FiD, an encoder-decoder multi-modal fusion-in-decoder model, for generating a textual answer for KI-VQA tasks.
You can't pick your neighbors, or can you? When and how to rely on retrieval in the $k$NN-LM
Retrieval-enhanced language models (LMs), which condition their predictions on text retrieved from large external datastores, have recently shown significant perplexity improvements compared to standard LMs.
Ranked #9 on
Language Modelling
on WikiText-103
A Personalized Dense Retrieval Framework for Unified Information Access
Developing a universal model that can efficiently and effectively respond to a wide range of information access requests -- from retrieval to recommendation to question answering -- has been a long-lasting goal in the information retrieval community.
Large Language Model Augmented Narrative Driven Recommendations
Narrative-driven recommendation (NDR) presents an information access problem where users solicit recommendations with verbose descriptions of their preferences and context, for example, travelers soliciting recommendations for points of interest while describing their likes/dislikes and travel circumstances.
Neural Ranking Models with Weak Supervision
Our experiments indicate that employing proper objective functions and letting the networks to learn the input representation based on weakly supervised data leads to impressive performance, with over 13% and 35% MAP improvements over the BM25 model on the Robust and the ClueWeb collections.
Ranked #8 on
Ad-Hoc Information Retrieval
on TREC Robust04
(MAP metric)
Pre-Training Multi-Modal Dense Retrievers for Outside-Knowledge Visual Question Answering
The proposed approach leads to 26. 9% Precision@5 improvements compared to the current state-of-the-art asymmetric architecture.
Analysing Mixed Initiatives and Search Strategies during Conversational Search
In this paper, we present a model for conversational search -- from which we instantiate different observed conversational search strategies, where the agent elicits: (i) Feedback-First, or (ii) Feedback-After.
Editable User Profiles for Controllable Text Recommendation
Finally, we implement LACE in an interactive controllable recommender system and conduct a user study to demonstrate that users are able to improve the quality of recommendations they receive through interactions with an editable user profile.
Relevance-based Word Embedding
This is the motivation for developing unsupervised relevance-based word embedding models that learn word representations based on query-document relevance information.
Regression and Learning to Rank Aggregation for User Engagement Evaluation
In this paper, we consider a tweet containing a rating for a movie as an instance and focus on ranking the instances of each user based on their engagement, i. e., the total number of retweets and favorites it will gain.
An Analysis of Approaches Taken in the ACM RecSys Challenge 2018 for Automatic Music Playlist Continuation
We further report and analyze the results obtained by the top performing teams in each track and explore the approaches taken by the winners.
Neural Matching Models for Question Retrieval and Next Question Prediction in Conversation
We further evaluate the neural matching models in the next question prediction task in conversations.
A Deep Look into Neural Ranking Models for Information Retrieval
Ranking models lie at the heart of research on information retrieval (IR).
Investigating the Successes and Failures of BERT for Passage Re-Ranking
The bidirectional encoder representations from transformers (BERT) model has recently advanced the state-of-the-art in passage re-ranking.
ANTIQUE: A Non-Factoid Question Answering Benchmark
Despite the importance of the task, the community still feels the significant lack of large-scale non-factoid question answering collections with real questions and comprehensive relevance judgments.
Recommender Systems Fairness Evaluation via Generalized Cross Entropy
We present a probabilistic framework based on generalized cross entropy to evaluate fairness of recommender systems under this perspective, where we show that the proposed framework is flexible and explanatory by allowing to incorporate domain knowledge (through an ideal fair distribution) that can help to understand which item or user aspects a recommendation algorithm is over- or under-representing.
Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering
Multi-hop question answering (QA) requires an information retrieval (IR) system that can find \emph{multiple} supporting evidence needed to answer the question, making the retrieval process very challenging.
Common Conversational Community Prototype: Scholarly Conversational Assistant
This paper discusses the potential for creating academic resources (tools, data, and evaluation approaches) to support research in conversational search, by focusing on realistic information needs and conversational interactions.
Analyzing and Learning from User Interactions for Search Clarification
We also propose a model for learning representation for clarifying questions based on the user interaction data as implicit feedback.
Guided Transformer: Leveraging Multiple External Sources for Representation Learning in Conversational Search
Asking clarifying questions in response to ambiguous or faceted queries has been recognized as a useful technique for various information retrieval systems, especially conversational search systems with limited bandwidth interfaces.
Conformer-Kernel with Query Term Independence at TREC 2020 Deep Learning Track
We benchmark Conformer-Kernel models under the strict blind evaluation setting of the TREC 2020 Deep Learning track.
Tip of the Tongue Known-Item Retrieval: A Case Study in Movie Identification
Using movie search as a case study, we explore the characteristics of questions posed by searchers in TOT states in a community question answering website.
Improving Transformer-Kernel Ranking Model Using Conformer and Query Term Independence
The Transformer-Kernel (TK) model has demonstrated strong reranking performance on the TREC Deep Learning benchmark -- and can be considered to be an efficient (but slightly less effective) alternative to other Transformer-based architectures that employ (i) large-scale pretraining (high training cost), (ii) joint encoding of query and document (high inference cost), and (iii) larger number of Transformer layers (both high training and high inference costs).
Current Challenges and Future Directions in Podcast Information Access
Podcasts are spoken documents across a wide-range of genres and styles, with growing listenership across the world, and a rapidly lowering barrier to entry for both listeners and creators.
DISAPERE: A Dataset for Discourse Structure in Peer Review Discussions
At the foundation of scientific evaluation is the labor-intensive process of peer review.
Explaining Documents' Relevance to Search Queries
GenEx explains a search result by providing a terse description for the query aspect covered by that result.
Conversational Information Seeking
Conversational information seeking (CIS) is concerned with a sequence of interactions between one or more users and an information system.
Retrieval-Enhanced Machine Learning
Although information access systems have long supported people in accomplishing a wide range of tasks, we propose broadening the scope of users of information access systems to include task-driven machines, such as machine learning models.
MIMICS-Duo: Offline & Online Evaluation of Search Clarification
Asking clarification questions is an active area of research; however, resources for training and evaluating search clarification methods are not sufficient.
Are We There Yet? A Decision Framework for Replacing Term Based Retrieval with Dense Retrieval Systems
Recently, several dense retrieval (DR) models have demonstrated competitive performance to term-based retrieval that are ubiquitous in search systems.
Multi-Task Retrieval-Augmented Text Generation with Relevance Sampling
This paper studies multi-task training of retrieval-augmented generation models for knowledge-intensive tasks.
FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation
Retrieval-augmented generation models offer many benefits over standalone language models: besides a textual answer to a given query they provide provenance items retrieved from an updateable knowledge base.
Generalized Weak Supervision for Neural Information Retrieval
To address this issue, one can train NRMs via weak supervision, where a large dataset is automatically generated using an existing ranking model (called the weak labeler) for training NRMs.
Multivariate Representation Learning for Information Retrieval
Instead of learning a vector for each query and document, our framework learns a multivariate distribution and uses negative multivariate KL divergence to compute the similarity between distributions.
Soft Prompt Decoding for Multilingual Dense Retrieval
In this work, we explore a Multilingual Information Retrieval (MLIR) task, where the collection includes documents in multiple languages.
Cross-Lingual Information Retrieval
Knowledge Distillation
+1
ICXML: An In-Context Learning Framework for Zero-Shot Extreme Multi-Label Classification
This paper focuses on the task of Extreme Multi-Label Classification (XMC) whose goal is to predict multiple labels for each instance from an extremely large label space.
Online and Offline Evaluation in Search Clarification
The effectiveness of clarification question models in engaging users within search systems is currently constrained, casting doubt on their overall usefulness.
Evaluating Retrieval Quality in Retrieval-Augmented Generation
Furthermore, evaluation of the retrieval model's performance based on query-document relevance labels shows a small correlation with the RAG system's downstream performance.
